jvitorcosta/python-uv-claude-template
Copier template: Python + uv + ruff + mypy + pytest + Makefile + full Claude Code setup
stack: Python
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
5/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · Sandbox or ask-first rules · details
Quality 26/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit jvitorcosta/python-uv-claude-template/template/.claude ./rig-python-uv-claude-template # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit jvitorcosta/python-uv-claude-template/template/.claude/skills/release .claude/skills/release $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/jvitorcosta/python-uv-claude-template/main/template/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-auditor.md https://raw.githubusercontent.com/jvitorcosta/python-uv-claude-template/main/template/.claude/agents/security-auditor.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(./**/*.pem)",
"Read(./**/*.key)",
"Bash(pip install:*)",
"Bash(sudo:*)"
],
"ask": [
"Bash(git push:*)",
"Bash(uv publish:*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "uv run --no-project --quiet \"$CLAUDE_PROJECT_DIR/.claude/hooks/validate_bash.py\""
}
]
}
]
}
} Skills (1)
Subagents (2)
| code-reviewer model: sonnet | Reviews Python changes for correctness, readability, tests and adherence to project conventions. Use proactively after writing or modifying code, and for /review. |
| security-auditor model: sonnet | Audits code for security vulnerabilities (injection, secrets, unsafe deserialisation, path traversal, dependency risk). Use when changes touch input handling, subprocess, files, auth, network or confi |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | uv run --no-project --quiet "$CLAUDE_PROJECT_DIR/.claude/hooks/validate_bash.py" |
| PostToolUse | Edit|MultiEdit|Write | uv run --no-project --quiet "$CLAUDE_PROJECT_DIR/.claude/hooks/format_python.py" |
Slash commands (2)
/fix-issue/review
Permissions
deny (6)
Read(./.env)
Read(./.env.*)
Read(./**/*.pem)
Read(./**/*.key)
Bash(pip install:*)
Bash(sudo:*)
ask (2)
Bash(git push:*)
Bash(uv publish:*)
allow (13)
Bash(make:*)
Bash(uv run:*)
Bash(uv sync:*)
Bash(uv add:*)
Bash(uv remove:*)
Bash(uv lock:*)
Bash(uv tree:*)
Bash(git status:*)
Bash(git diff:*)
Bash(git log:*)
Bash(git switch:*)
Bash(gh issue view:*)
Bash(gh pr view:*)
Similar rigs
carlosp5751258-lgtm/ctrlia-que-pieza-usar
Claude Code: skills vs hooks, MCP, subagentes y plugins
Minimalist 65 tok · · Q15
MCKRUZ/claude-code-mastery
The definitive Claude Code setup, configuration, and mastery skill — CLAUDE.md engineering, MCP servers, agent teams, hooks, CI/CD, and self-updating knowledge base
Minimalist 1.0k tok · · Q0
maryam-bahrami/claude-code-project-structure
A practical Claude Code project template showcasing best practices for CLAUDE.md, commands, skills, agents, MCP integrations, and team workflows.
Pragmatist 3.0k tok · · Q18
Mathiew82/minimal-claudeness
A minimal, dependency-free meta-harness for Claude Code.
Pragmatist 2.7k tok · · Q20